Skip to main content
Disciplines
Automotive Business IT + Informatics Construction + Real Estate Electrical Engineering + Electronics Energy + Sustainability Insurance + Risk Finance + Banking Management + Leadership Marketing + Sales Mechanical Engineering + Materials
Events
DE
EN
Books
Journals
Topic Page
Marketing
Start single access now
Access for companies
EXTENDED SEARCH
Log in
Top
Published in:
Adaptive Future Frame Prediction with Ensemble Network Read chapter Read first chapter

2021 | OriginalPaper | Chapter

Survey on Deep Learning-Based Kuzushiji Recognition

Authors : Kazuya Ueki, Tomoka Kojima

Published in: Pattern Recognition. ICPR International Workshops and Challenges

Publisher: Springer International Publishing

Log in

Activate our intelligent search to find suitable subject content or patents.

search-config
loading …

Abstract

Owing to the overwhelming accuracy of the deep learning method demonstrated at the 2012 image classification competition, deep learning has been successfully applied to a variety of other tasks. The high-precision detection and recognition of Kuzushiji, a Japanese cursive script used for transcribing historical documents, has been made possible through the use of deep learning. In recent years, competitions on Kuzushiji recognition have been held, and many researchers have proposed various recognition methods. This study examines recent research trends, current problems, and future prospects in Kuzushiji recognition using deep learning.

Dont have a licence yet? Then find out more about our products and how to get one now:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

inform now

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

inform now
previous chapter Can OpenPose Be Used as a 3D Registration Method for 3D Scans of Cultural Heritage Artifacts
next chapter Stylistic Classification of Historical Violins: A Deep Learning Approach
Footnotes
1
Hiragana is one of the three different character sets used in Japanese writing. Each Hiragana character represents a particular syllable. There are 46 basic characters.
 
2
Kanji is another one of the three character sets used in the Japanese language. Along with syllabaries, Kanji is made up of ideographic characters, and each letter symbolizes a specific meaning. Most Kanji characters were imported from China, although some were developed in Japan. Although there are approximately 50,000 Kanji characters, only approximately 2,500 are actually used in daily life in Japan.
 
3
A Jibo is a root Kanji character of Hiragana. For example, the character https://static-content.springer.com/image/chp%3A10.1007%2F978-3-030-68787-8_7/MediaObjects/510916_1_En_7_Figa_HTML.gif is derived from different Jibos including https://static-content.springer.com/image/chp%3A10.1007%2F978-3-030-68787-8_7/MediaObjects/510916_1_En_7_Figb_HTML.gif and https://static-content.springer.com/image/chp%3A10.1007%2F978-3-030-68787-8_7/MediaObjects/510916_1_En_7_Figc_HTML.gif
 
4
In the same way as Hiragana, Katakana is one of the three different character sets used in Japanese. Katakana is also a phonetic syllabary, in which each letter represents the sound of a syllable. There are also 46 basic characters.
 
9
A contest held annually by the Pattern Recognition and Media Understanding (PRMU) for the purpose of revitalizing research group activities.
 
11
One book was eliminated from the competition.
 
12
Furigana is made up of phonetic symbols occasionally written next to difficult or rare Kanji to show their pronunciation.
 
14
A set of technology standards intended to make it easier for researchers, students, and the public at large to view, manipulate, compare, and annotate digital images on the web. https://​iiif.​io/​.
 
Literature
1.
Yamada, S., et al.: Historical character recognition (HCR) project report (2). IPSJ SIG Comput. Hum. (CH) 50(2), 9–16 (2001). (in Japanese)
2.
Yamada, S., Waizumi, Y., Kato, N., Shibayama, M.: Development of a digital dictionary of historical characters with search function of similar characters. IPSJ SIG Comput. Hum. (CH) 54(7), 43–50 (2002). (in Japanese)
3.
Onuma, M., Zhu, B., Yamada, S., Shibayama, M., Nakagawa, M.: Development of cursive character pattern recognition for accessing a digital dictionary to support decoding of historical documents. IEICE Technical Report, vol. 106, no. 606, PRMU2006-270, pp. 91–96 (2007). (in Japanese)
4.
Horiuchi, T., Kato, S.: A study on Japanese historical character recognition using modular neural networks. Int. J. Innov. Comput. Inf. Control 7(8), 5003–5014 (2011)
5.
Kato, S., Asano, R.: A study on historical character recognition by using SOM template. In: Proceedings of 30th Fuzzy System Symposium, pp. 242–245 (2014). (in Japanese)
6.
Hayasaka, T., Ohno, W., Kato, Y.: Recognition of obsolete script in pre-modern Japanese texts by Neocognitron. J. Toyota Coll. Technol. 48, 5–12 (2015). (in Japanese)
7.
Hayasaka, T., Ohno, W., Kato, Y., Yamamoto, K.: Recognition of hentaigana by deep learning and trial production of WWW application. In: Proceedings of IPSJ Symposium of Humanities and Computer Symposium, pp. 7–12 (2016). (in Japanese)
8.
Ueda, K., Sonogashira, M., Iiyama, M.: Old Japanese character recognition by convolutional neural net and character aspect ratio. ELCAS J. 3, 88–90 (2018). (in Japanese)
9.
Kojima, T., Ueki, K.: Utilization and analysis of deep learning for Kuzushiji translation. J. Japan Soc. Precis. Eng. 85(12), 1081–1086 (2019). (in Japanese)CrossRef
10.
Yang, Z., Doman, K., Yamada, M., Mekada, Y.: Character recognition of modern Japanese official documents using CNN for imblanced learning data. In: Proceedings of 2019 International Workshop on Advanced Image Technology (IWAIT), no. 74 (2019)
11.
Nagai, A.: Recognizing three character string of old Japanese cursive by convolutional neural networks. In: Proceedings of Information Processing Society of Japan (IPSJ) Symposium, pp. 213–218 (2017). (in Japanese)
12.
Ueki, K., Kojima, T., Mutou, R., Nezhad, R.S., Hagiwara, Y.: Recognition of Japanese connected cursive characters using multiple softmax outputs. In: Proceedings of International Conference on Multimedia Information Processing and Retrieval (2020)
13.
Hu, X., Inamoto, M., Konagaya, A.: Recognition of Kuzushi-ji with deep learning method: a case study of Kiritsubo chapter in the tale of Genji. In: The 33rd Annual Conference of the Japanese Society for Artificial Intelligence (2019)
14.
Kitamoto, A., Clanuwat, T., Miyazaki, T., Yayamoto, K.: Analysis of character data: potential and impact of Kuzushiji recognition by machine learning. J. Inst. Electron. Inf. Commun. Eng. 102(6), 563–568 (2019). (in Japanese)
15.
Kitamoto, A., Clanuwat, T., Lamb, A., Bober-Irizar, M.: Progress and results of kaggle machine learning competition for Kuzushiji recognition. In: Proceedings of the Computers and the Humanities Symposium, pp. 223–230 (2019). (in Japanese)
16.
Kitamoto, A., Clanuwat, T., Bober-Irizar, M.: Kaggle Kuzushiji recognition competition - challenges of hosting a world-wide competition in the digital humanities. J. Japanese Soc. Artif. Intell. 35(3), 366–376 (2020). (in Japanese)
17.
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. arXiv:​1506.​01497 (2015)
18.
19.
Clanuwat, T., Lamb, A., Kitamoto, A.: KuroNet: pre-modern Japanese Kuzushiji character recognition with deep learning. In: Proceedings of International Conference on Document Analysis and Recognition (ICDAR2019) (2019)
20.
Lamb, A., Clanuwat, T., Kitamoto, A.: KuroNet: regularized residual U-nets for end-to-end Kuzushiji character recognition. In: Proceedings of SN Computer Science (2020)
21.
Le, A.D., Clanuwat, T., Kitamoto, A.: A human-inspired recognition system for premodern Japanese historical documents. arXiv:​1905.​05377 (2019)
22.
Le, A.D.: Automated Transcription for Pre-Modern Japanese Kuzushiji Documents by Random Lines Erasure and Curriculum Learning. arXiv:​2005.​02669 (2020)
23.
Le, A.D.: Detecting Kuzushiji characters from historical documents by two-dimensional context box proposal network. Future Data Secur. Eng. 731–738
24.
Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural Netw. 18(5–6), 602–610 (2005)CrossRef
25.
Yamamoto, S., Tomejiro, O.: Labor saving for reprinting Japanese rare classical books. J. Inf. Process. Manag. 58(11), 819–827 (2016). (in Japanese)
26.
Ueki, K., Kojima, T.: Feasibility study of deep learning based Japanese cursive character recognition. IIEEJ Trans. Image Electron. Vis. Comput. 8(1), 10–16 (2020)
27.
Ueki, K., Kojima, T.: Japanese cursive character recognition for efficient transcription. In: Proceedings of the International Conference on Pattern Recognition Applications and Methods (2020)
28.
Takeuchi, M.: Development of embedded system for recognizing Kuzushiji by deep learning. In: Proceedings of the 33rd Annual Conference of the Japanese Society for Artificial Intelligence (2019). (in Japanese)
29.
Sando, K., Suzuki, T., Aiba, A.: A constraint solving web service for recognizing historical Japanese KANA texts. In: Proceedings of the 10th International Conference on Agents and Artificial Intelligence (ICAART) (2018)
30.
Yamazaki, A., Suzuki, T., Sando, K., Aiba, A.: A handwritten Japanese historical kana reprint support system. In: Proceedings of the 18th ACM Symposium on Document Engineering (2018)
31.
Panichkriangkrai, C., Li, L., Kaneko, T., Akama, R., Hachimura, K.: Character segmentation and transcription system for historical Japanese books with a self-proliferating character image database. Int. J. Doc. Anal. Recogn. (IJDAR) 20, 241–257 (2017)CrossRef
32.
Clanuwat, T., Bober-Irizar, M., Kitamoto, A., Lamb, A., Yamamoto, K., Ha, D.: Deep learning for classical Japanese literature. arXiv:​1812.​01718 (2018)
33.
Nguyen, H.T., Ly, N.T., Nguyen, K.C., Nguyen, C.T., Nakagawa, M.: Attempts to recognize anomalously deformed Kana in Japanese historical documents. In: Proceedings of the International Workshop on Historical Document Imaging and Processing (HIP 2017) (2017)
34.
Graves, A., Fernandez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: Proceedings of the International Conference on Machine Learning, pp. 369–376 (2006)
35.
Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1724–1734 (2014)
36.
37.
Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-CAM: Visual Explanations from Deep Networks via Gradientbased Localization. arXiv:​1610.​02391 (2016)
38.
39.
40.
Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2020)
41.
Xie, S., Girshick, R., Dollár, P., Tu, Z., He, K.: Aggregated residual transformation for deep neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017)
42.
Ke, G., et al.: LightGBM: a highly efficient gradient boosting decision tree. Adv. Neural Inf. Process. Syst. (NIPS) 30, 3148–3156 (2017)
43.
44.
45.
46.
Takahashi, R., Matsubara, T., Uehara, K.: Data Augmentation using Random Image Cropping and Patching for Deep CNNs. arXiv:​1811.​09030 (2018)
47.
Chen, K., et al.: Hybrid task cascade for instance segmentation. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4974–4983 (2019)
48.
Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting Text in Natural Image with Connectionist Text Proposal Network. arXiv:​1609.​03605 (2016)
49.
Heafield, K.: KenLM: faster and smaller language model queries. In: Proceedings of the Sixth Workshop on Statistical Machine Translation, pp. 187–197 (2011)
50.
Kim, S., Hori, T., Watanabe, S.: Joint CTC-attention based end-to-end speech recognition using multi-task learning. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2017)
51.
52.
53.
Metadata
Title
Survey on Deep Learning-Based Kuzushiji Recognition
Authors
Kazuya Ueki
Tomoka Kojima
Copyright Year
2021
Book
Pattern Recognition. ICPR International Workshops and Challenges

Print ISBN: 978-3-030-68786-1

Electronic ISBN: 978-3-030-68787-8

Copyright Year: 2021

DOI
https://doi.org/10.1007/978-3-030-68787-8_7

Premium Partner

    Image Credits